PyTorchKR Papers

최신 논문

총 561편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1304.7820

Challenges on Probabilistic Modeling for Evolving Networks

With the emerging of new networks, such as wireless sensor networks, vehicle networks, P2P networks, cloud computing, mobile Internet, or social networks, the network dynamics and complexity expands from system design, hardware, software, protocols, structures, integration, evolution, application, even to business goals. Thus the dynamics and uncertainty are unavoidable characteristics, which come from the regular network evolution and unexpected hardware defects, unavoidable software errors, incomplete management information and dependency relationship between the entities among the emerging complex networks. Due to the complexity of emerging networks, it is not always possible to build precise models in modeling and optimization (local and global) for networks. This paper presents a survey on probabilistic modeling for evolving networks and identifies the new challenges which emerge on the probabilistic models and optimization strategies in the potential application areas of network performance, network management and network security for evolving networks.

arXiv:1305.4228

The state-of-the-art in web-scale semantic information processing for cloud computing

Based on integrated infrastructure of resource sharing and computing in distributed environment, cloud computing involves the provision of dynamically scalable and provides virtualized resources as services over the Internet. These applications also bring a large scale heterogeneous and distributed information which pose a great challenge in terms of the semantic ambiguity. It is critical for application services in cloud computing environment to provide users intelligent service and precise information. Semantic information processing can help users deal with semantic ambiguity and information overload efficiently through appropriate semantic models and semantic information processing technology. The semantic information processing have been successfully employed in many fields such as the knowledge representation, natural language understanding, intelligent web search, etc. The purpose of this report is to give an overview of existing technologies for semantic information processing in cloud computing environment, to propose a research direction for addressing distributed semantic reasoning and parallel semantic computing by exploiting semantic information newly available in cloud computing environment.

arXiv:1312.4108

A MapReduce based distributed SVM algorithm for binary classification

Although Support Vector Machine (SVM) algorithm has a high generalization property to classify for unseen examples after training phase and it has small loss value, the algorithm is not suitable for real-life classification and regression problems. SVMs cannot solve hundreds of thousands examples in training dataset. In previous studies on distributed machine learning algorithms, SVM is trained over a costly and preconfigured computer environment. In this research, we present a MapReduce based distributed parallel SVM training algorithm for binary classification problems. This work shows how to distribute optimization problem over cloud computing systems with MapReduce technique. In the second step of this work, we used statistical learning theory to find the predictive hypothesis that minimize our empirical risks from hypothesis spaces that created with reduce function of MapReduce. The results of this research are important for training of big datasets for SVM algorithm based classification problems. We provided that iterative training of split dataset with MapReduce technique; accuracy of the classifier function will converge to global optimal classifier function's accuracy in finite iteration size. The algorithm performance was measured on samples from letter recognition and pen-based recognition of handwritten digits dataset.

arXiv:1404.5528

Hybrid Genetic Algorithm for Cloud Computing Applications

In this paper with the aid of genetic algorithm and fuzzy theory, we present a hybrid job scheduling approach, which considers the load balancing of the system and reduces total execution time and execution cost. We try to modify the standard Genetic algorithm and to reduce the iteration of creating population with the aid of fuzzy theory. The main goal of this research is to assign the jobs to the resources with considering the VM MIPS and length of jobs. The new algorithm assigns the jobs to the resources with considering the job length and resources capacities. We evaluate the performance of our approach with some famous cloud scheduling models. The results of the experiments show the efficiency of the proposed approach in term of execution time, execution cost and average Degree of Imbalance (DI).

arXiv:1406.5161

Fast Support Vector Machines Using Parallel Adaptive Shrinking on Distributed Systems

Support Vector Machines (SVM), a popular machine learning technique, has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. Whether it is identifying high-risk patients by health-care professionals, or potential high-school students to enroll in college by school districts, SVMs can play a major role for social good. This paper undertakes the challenge of designing a scalable parallel SVM training algorithm for large scale systems, which includes commodity multi-core machines, tightly connected supercomputers and cloud computing systems. Intuitive techniques for improving the time-space complexity including adaptive elimination of samples for faster convergence and sparse format representation are proposed. Under sample elimination, several heuristics for {\em earliest possible} to {\em lazy} elimination of non-contributing samples are proposed. In several cases, where an early sample elimination might result in a false positive, low overhead mechanisms for reconstruction of key data structures are proposed. The algorithm and heuristics are implemented and evaluated on various publicly available datasets. Empirical evaluation shows up to 26x speed improvement on some datasets against the sequential baseline, when evaluated on multiple compute nodes, and an improvement in execution time up to 30-60\% is readily observed on a number of other datasets against our parallel baseline.

arXiv:1411.4379

FGPGA: An Efficient Genetic Approach for Producing Feasible Graph Partitions

Graph partitioning, a well studied problem of parallel computing has many applications in diversified fields such as distributed computing, social network analysis, data mining and many other domains. In this paper, we introduce FGPGA, an efficient genetic approach for producing feasible graph partitions. Our method takes into account the heterogeneity and capacity constraints of the partitions to ensure balanced partitioning. Such approach has various applications in mobile cloud computing that include feasible deployment of software applications on the more resourceful infrastructure in the cloud instead of mobile hand set. Our proposed approach is light weight and hence suitable for use in cloud architecture. We ensure feasibility of the partitions generated by not allowing over-sized partitions to be generated during the initialization and search. Our proposed method tested on standard benchmark datasets significantly outperforms the state-of-the-art methods in terms of quality of partitions and feasibility of the solutions.

arXiv:1412.6149

Design, Implementation and Simulation of a Cloud Computing System for Enhancing Real-time Video Services by using VANET and Onboard Navigation Systems

In this paper, we propose a design for novel and experimental cloud computing systems. The proposed system aims at enhancing computational, communicational and annalistic capabilities of road navigation services by merging several independent technologies, namely vision-based embedded navigation systems, prominent Cloud Computing Systems (CCSs) and Vehicular Ad-hoc NETwork (VANET). This work presents our initial investigations by describing the design of a global generic system. The designed system has been experimented with various scenarios of video-based road services. Moreover, the associated architecture has been implemented on a small-scale simulator of an in-vehicle embedded system. The implemented architecture has been experimented in the case of a simulated road service to aid the police agency. The goal of this service is to recognize and track searched individuals and vehicles in a real-time monitoring system remotely connected to moving cars. The presented work demonstrates the potential of our system for efficiently enhancing and diversifying real-time video services in road environments.

arXiv:1503.06424

Modeling browser-based distributed evolutionary computation systems

From the era of big science we are back to the "do it yourself", where you do not have any money to buy clusters or subscribe to grids but still have algorithms that crave many computing nodes and need them to measure scalability. Fortunately, this coincides with the era of big data, cloud computing, and browsers that include JavaScript virtual machines. Those are the reasons why this paper will focus on two different aspects of volunteer or freeriding computing: first, the pragmatic: where to find those resources, which ones can be used, what kind of support you have to give them; and then, the theoretical: how evolutionary algorithms can be adapted to an environment in which nodes come and go, have different computing capabilities and operate in complete asynchrony of each other. We will examine the setup needed to create a very simple distributed evolutionary algorithm using JavaScript and then find a model of how users react to it by collecting data from several experiments featuring different classical benchmark functions.

arXiv:1502.03302

Using Distance Estimation and Deep Learning to Simplify Calibration in Food Calorie Measurement

High calorie intake in the human body on the one hand, has proved harmful in numerous occasions leading to several diseases and on the other hand, a standard amount of calorie intake has been deemed essential by dieticians to maintain the right balance of calorie content in human body. As such, researchers have proposed a variety of automatic tools and systems to assist users measure their calorie in-take. In this paper, we consider the category of those tools that use image processing to recognize the food, and we propose a method for fully automatic and user-friendly calibration of the dimension of the food portion sizes, which is needed in order to measure food portion weight and its ensuing amount of calories. Experimental results show that our method, which uses deep learning, mobile cloud computing, distance estimation and size calibration inside a mobile device, leads to an accuracy improvement to 95% on average compared to previous work

arXiv:1506.00227

Parallel Spectral Clustering Algorithm Based on Hadoop

Spectral clustering and cloud computing is emerging branch of computer science or related discipline. It overcome the shortcomings of some traditional clustering algorithm and guarantee the convergence to the optimal solution, thus have to the widespread attention. This article first introduced the parallel spectral clustering algorithm research background and significance, and then to Hadoop the cloud computing Framework has carried on the detailed introduction, then has carried on the related to spectral clustering is introduced, then introduces the spectral clustering arithmetic Method of parallel and relevant steps, finally made the related experiments, and the experiment are summarized.

arXiv:1510.02055

Diverse Large-Scale ITS Dataset Created from Continuous Learning for Real-Time Vehicle Detection

In traffic engineering, vehicle detectors are trained on limited datasets resulting in poor accuracy when deployed in real world applications. Annotating large-scale high quality datasets is challenging. Typically, these datasets have limited diversity; they do not reflect the real-world operating environment. There is a need for a large-scale, cloud based positive and negative mining (PNM) process and a large-scale learning and evaluation system for the application of traffic event detection. The proposed positive and negative mining process addresses the quality of crowd sourced ground truth data through machine learning review and human feedback mechanisms. The proposed learning and evaluation system uses a distributed cloud computing framework to handle data-scaling issues associated with large numbers of samples and a high-dimensional feature space. The system is trained using AdaBoost on $1,000,000$ Haar-like features extracted from $70,000$ annotated video frames. The trained real-time vehicle detector achieves an accuracy of at least $95\%$ for $1/2$ and about $78\%$ for $19/20$ of the time when tested on approximately $7,500,000$ video frames. At the end of 2015, the dataset is expect to have over one billion annotated video frames.

arXiv:1510.02709공식 코드 · Papers with Code

Large-scale Artificial Neural Network: MapReduce-based Deep Learning

Faced with continuously increasing scale of data, original back-propagation neural network based machine learning algorithm presents two non-trivial challenges: huge amount of data makes it difficult to maintain both efficiency and accuracy; redundant data aggravates the system workload. This project is mainly focused on the solution to the issues above, combining deep learning algorithm with cloud computing platform to deal with large-scale data. A MapReduce-based handwriting character recognizer will be designed in this project to verify the efficiency improvement this mechanism will achieve on training and practical large-scale data. Careful discussion and experiment will be developed to illustrate how deep learning algorithm works to train handwritten digits data, how MapReduce is implemented on deep learning neural network, and why this combination accelerates computation. Besides performance, the scalability and robustness will be mentioned in this report as well. Our system comes with two demonstration software that visually illustrates our handwritten digit recognition/encoding application.

arXiv:1509.05177

Some Theorems for Feed Forward Neural Networks

In this paper we introduce a new method which employs the concept of "Orientation Vectors" to train a feed forward neural network and suitable for problems where large dimensions are involved and the clusters are characteristically sparse. The new method is not NP hard as the problem size increases. We `derive' the method by starting from Kolmogrov's method and then relax some of the stringent conditions. We show for most classification problems three layers are sufficient and the network size depends on the number of clusters. We prove as the number of clusters increase from N to N+dN the number of processing elements in the first layer only increases by d(logN), and are proportional to the number of classes, and the method is not NP hard. Many examples are solved to demonstrate that the method of Orientation Vectors requires much less computational effort than Radial Basis Function methods and other techniques wherein distance computations are required, in fact the present method increases logarithmically with problem size compared to the Radial Basis Function method and the other methods which depend on distance computations e.g statistical methods where probabilistic distances are calculated. A practical method of applying the concept of Occum's razor to choose between two architectures which solve the same classification problem has been described. The ramifications of the above findings on the field of Deep Learning have also been briefly investigated and we have found that it directly leads to the existence of certain types of NN architectures which can be used as a "mapping engine", which has the property of "invertibility", thus improving the prospect of their deployment for solving problems involving Deep Learning and hierarchical classification. The latter possibility has a lot of future scope in the areas of machine learning and cloud computing.

arXiv:1504.00981

ELM-Based Distributed Cooperative Learning Over Networks

This paper investigates distributed cooperative learning algorithms for data processing in a network setting. Specifically, the extreme learning machine (ELM) is introduced to train a set of data distributed across several components, and each component runs a program on a subset of the entire data. In this scheme, there is no requirement for a fusion center in the network due to e.g., practical limitations, security, or privacy reasons. We first reformulate the centralized ELM training problem into a separable form among nodes with consensus constraints. Then, we solve the equivalent problem using distributed optimization tools. A new distributed cooperative learning algorithm based on ELM, called DC-ELM, is proposed. The architecture of this algorithm differs from that of some existing parallel/distributed ELMs based on MapReduce or cloud computing. We also present an online version of the proposed algorithm that can learn data sequentially in a one-by-one or chunk-by-chunk mode. The novel algorithm is well suited for potential applications such as artificial intelligence, computational biology, finance, wireless sensor networks, and so on, involving datasets that are often extremely large, high-dimensional and located on distributed data sources. We show simulation results on both synthetic and real-world data sets.

arXiv:1508.01633

Asynchronous Distributed Semi-Stochastic Gradient Optimization

With the recent proliferation of large-scale learning problems,there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its variants. However, existing algorithms either suffer from slow convergence due to the inherent variance of stochastic gradients, or have a fast linear convergence rate but at the expense of poorer solution quality. In this paper, we combine their merits by proposing a fast distributed asynchronous SGD-based algorithm with variance reduction. A constant learning rate can be used, and it is also guaranteed to converge linearly to the optimal solution. Experiments on the Google Cloud Computing Platform demonstrate that the proposed algorithm outperforms state-of-the-art distributed asynchronous algorithms in terms of both wall clock time and solution quality.

arXiv:1602.06489

Distributed Private Online Learning for Social Big Data Computing over Data Center Networks

With the rapid growth of Internet technologies, cloud computing and social networks have become ubiquitous. An increasing number of people participate in social networks and massive online social data are obtained. In order to exploit knowledge from copious amounts of data obtained and predict social behavior of users, we urge to realize data mining in social networks. Almost all online websites use cloud services to effectively process the large scale of social data, which are gathered from distributed data centers. These data are so large-scale, high-dimension and widely distributed that we propose a distributed sparse online algorithm to handle them. Additionally, privacy-protection is an important point in social networks. We should not compromise the privacy of individuals in networks, while these social data are being learned for data mining. Thus we also consider the privacy problem in this article. Our simulations shows that the appropriate sparsity of data would enhance the performance of our algorithm and the privacy-preserving method does not significantly hurt the performance of the proposed algorithm.

arXiv:1603.08767

Machine Learning and Cloud Computing: Survey of Distributed and SaaS Solutions

Applying popular machine learning algorithms to large amounts of data raised new challenges for the ML practitioners. Traditional ML libraries does not support well processing of huge datasets, so that new approaches were needed. Parallelization using modern parallel computing frameworks, such as MapReduce, CUDA, or Dryad gained in popularity and acceptance, resulting in new ML libraries developed on top of these frameworks. We will briefly introduce the most prominent industrial and academic outcomes, such as Apache Mahout, GraphLab or Jubatus. We will investigate how cloud computing paradigm impacted the field of ML. First direction is of popular statistics tools and libraries (R system, Python) deployed in the cloud. A second line of products is augmenting existing tools with plugins that allow users to create a Hadoop cluster in the cloud and run jobs on it. Next on the list are libraries of distributed implementations for ML algorithms, and on-premise deployments of complex systems for data analytics and data mining. Last approach on the radar of this survey is ML as Software-as-a-Service, several BigData start-ups (and large companies as well) already opening their solutions to the market.

arXiv:1603.08071

Classification of Large-Scale Fundus Image Data Sets: A Cloud-Computing Framework

Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1% in 792 seconds. Also, for classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85% and 72% are observed, respectively. For images from STARE data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5% in 326 seconds. Such cloud-based fundus image analysis systems can significantly enhance the borderline classification performances in automated screening systems.

arXiv:1605.06940

Elastic Solver: Balancing Solution Time and Energy Consumption

Combinatorial decision problems arise in many different domains such as scheduling, routing, packing, bioinformatics, and many more. Despite recent advances in developing scalable solvers, there are still many problems which are often very hard to solve. Typically the most advanced solvers include elements which are stochastic in nature. If a same instance is solved many times using different seeds then depending on the inherent characteristics of a problem instance and the solver, one can observe a highly-variant distribution of times spanning multiple orders of magnitude. Therefore, to solve a problem instance efficiently it is often useful to solve the same instance in parallel with different seeds. With the proliferation of cloud computing, it is natural to think about an elastic solver which can scale up by launching searches in parallel on thousands of machines (or cores). However, this could result in consuming a lot of energy. Moreover, not every instance would require thousands of machines. The challenge is to resolve the tradeoff between solution time and energy consumption optimally for a given problem instance. We analyse the impact of the number of machines (or cores) on not only solution time but also on energy consumption. We highlight that although solution time always drops as the number of machines increases, the relation between the number of machines and energy consumption is more complicated. In many cases, the optimal energy consumption may be achieved by a middle ground, we analyse this relationship in detail. The tradeoff between solution time and energy consumption is studied further, showing that the energy consumption of a solver can be reduced drastically if we increase the solution time marginally. We also develop a prediction model, demonstrating that such insights can be exploited to achieve faster solutions times in a more energy efficient manor.

arXiv:1606.05675

DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment

Worldwide, in 2014, more than 1.9 billion adults, 18 years and older, were overweight. Of these, over 600 million were obese. Accurately documenting dietary caloric intake is crucial to manage weight loss, but also presents challenges because most of the current methods for dietary assessment must rely on memory to recall foods eaten. The ultimate goal of our research is to develop computer-aided technical solutions to enhance and improve the accuracy of current measurements of dietary intake. Our proposed system in this paper aims to improve the accuracy of dietary assessment by analyzing the food images captured by mobile devices (e.g., smartphone). The key technique innovation in this paper is the deep learning-based food image recognition algorithms. Substantial research has demonstrated that digital imaging accurately estimates dietary intake in many environments and it has many advantages over other methods. However, how to derive the food information (e.g., food type and portion size) from food image effectively and efficiently remains a challenging and open research problem. We propose a new Convolutional Neural Network (CNN)-based food image recognition algorithm to address this problem. We applied our proposed approach to two real-world food image data sets (UEC-256 and Food-101) and achieved impressive results. To the best of our knowledge, these results outperformed all other reported work using these two data sets. Our experiments have demonstrated that the proposed approach is a promising solution for addressing the food image recognition problem. Our future work includes further improving the performance of the algorithms and integrating our system into a real-world mobile and cloud computing-based system to enhance the accuracy of current measurements of dietary intake.